From f347d5336fafb24ed6b3b10c99fb244d465269db Mon Sep 17 00:00:00 2001
From: Frank <frank@dankware>
Date: Sat, 22 Aug 2026 12:54:28 -0700
Subject: [PATCH] Set FASTGREEDY=0 default in env; add deployment notes

---
 scripts/frank-default-large.env | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/scripts/frank-default-large.env b/scripts/frank-default-large.env
index 4b623ae..2356d73 100644
--- a/scripts/frank-default-large.env
+++ b/scripts/frank-default-large.env
@@ -82,7 +82,12 @@ SPEC_DRAFT_P_SPLIT=0.10
 # --reasoning-budget -1 (unrestricted) and chat_template_kwargs
 # preserve_thinking=true (preserve thinking tokens across turns).
 #
-# For fast-greedy bench: comment out the --reasoning on line in serve script
-# and set FASTGREEDY=1 in env (see serve script FASTGREEDY section).
-# FASTGREEDY=1 flips to: reasoning off, argmax fastpath=1, sampling defaults.
-# FASTGREEDY=0 (default) uses the production values above.
+# FASTGREEDY mode: set to 1 for fast-greedy benchmark (card's default profile)
+# FASTGREEDY=0 (default): production chat config (reasoning on, argmax off)
+# FASTGREEDY=1: reasoning off, LLAMA_TARGET_GREEDY_ARGMAX_FASTPATH=1, deterministic
+#   sampler. Mirrors the card's 'fast greedy (default)' benchmark config.
+FASTGREEDY=0
+
+# For fast-greedy bench: set FASTGREEDY=1 above. This flips to: reasoning off,
+# argmax fastpath=1, sampling defaults. Deploy with
+# FASTGREEDY=1 ./deploy.sh dankclaw to test the fast-greedy profile.